Application of improved Q learning algorithm to job shop problem

Wang, Chao; Guo, Jing; Bao, Zhenqiang

doi:10.3724/sp.j.1087.2008.03268

Cited by 4 publications

(10 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although the optimal solution to the problem will eventually be found, each search process only randomly selects one dimension of a nectar source to search, which reduces the convergence speed and accuracy of the algorithm, and it is easy to fall into a local optimum. 44 Therefore, in the process of improving the artificial bee colony algorithm, the focus is to improve the convergence accuracy of the algorithm by increasing the number of dimensions for each update. However, if the number of updated dimensions is too large, a new nectar source that is very different from the original nectar source will be generated, which violates the principle of updating near the nectar source and is not conducive to the convergence of the ABC algorithm.…”

Section: Combination Model Of Abc and Rlmentioning

confidence: 99%

A self‐learning artificial bee colony algorithm based on reinforcement learning for a flexible job‐shop scheduling problem

Long

Zhang

et al. 2021

Concurrency and Computation

View full text Add to dashboard Cite

The flexible job-shop scheduling problem (FJSP) is currently one of the most critical issues in process planning and manufacturing. The FJSP is studied with the goal of achieving the shortest makespan. Recently, some intelligent optimization algorithms have been applied to solve FJSP, but the key parameters of intelligent optimization algorithms cannot be dynamically adjusted during the solution process. Thus, the solutions cannot best meet the needs of production. To solve the problems of slow convergence speed and reaching a local optimum with the artificial bee colony (ABC) algorithm, an improved self-learning artificial bee colony algorithm (SLABC) based on reinforcement learning (RL) is proposed. In the SLABC algorithm, the number of updated dimensions of the ABC algorithm can be intelligently selected according to the RL algorithm, which improves the convergence speed and accuracy. In addition, a self-learning model of the SLABC algorithm is constructed and analyzed using Q-learning as the learning method of the algorithm, and the state determination and reward methods of the RL algorithm are designed and included in the environment of the artificial bee colony algorithm.Finally, this article verifies that SLABC has excellent convergence speed and accuracy in solving FJSP through Brandimarte instances. K E Y W O R D Sartificial bee colony, flexible job-shop scheduling problem, reinforcement learning, self-learning artificial bee colony INTRODUCTIONThe flexible job-shop scheduling problem (FJSP) is an extension of the classic job-shop scheduling problem, and it is a complex combinatorial optimization problem. 1 The FJSP has been a research hotspot over the years. In recent years, artificial intelligence optimization algorithms such as the ant colony optimization algorithm (ACO), 2,3 genetic algorithm (GA), 4-6 bee colony algorithm, [7][8][9][10][11] and various hybrid algorithms [12][13][14][15] have been usedto solve this problem, and some progress has been achieved, but a set of completely good solutions has not yet been reached; therefore, there is room for further research on this problem.Job-shop scheduling is a processing resource allocation problem. It reasonably arranges production resources, processing time, processing sequence, and so on, according to existing constraints to obtain the optimal cost or efficiency. 16 Due to the NP-hard characteristics of the FJSP, it is difficult to achieve global optimization even for small problems. Therefore, many researchers have begun to develop more effective solutions to obtain near-optimal solutions. Because of this trend, to solve the combinatorial optimization problem, many optimization algorithms have been developed. Wang et al. 17 proposed a random weighted hybrid particle swarm optimization algorithm (PSO) based on the second-order oscillation,

show abstract

Section: Combination Model Of Abc and Rlmentioning

confidence: 99%

A self‐learning artificial bee colony algorithm based on reinforcement learning for a flexible job‐shop scheduling problem

Long

Zhang

et al. 2021

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…The parameters of the model are accurately inverted by the published epidemic data; and the epidemic trend is accurately predicted [2] .Professor Jianqiang Ren's three-step prediction model for the New Coronary Pneumonia epidemic based on machine learning, which introduced machine learning algorithms such as neural networks, random forests, long and short-term memory networks and sequence-to-sequence to predict the New Coronary Pneumonia epidemic, and achieved reliable results [3] . Professor Qiyun Wang proposed a combined COVID-19 prediction model based on the CEEMDAN-HURST algorithm for the new cases of COVID-19, which can effectively solve the problems of low prediction efficiency and low prediction accuracy commonly found in nonlinear time series prediction models [4] . Many other scholars have also proposed corresponding prediction methods, but considering the reasons for the mutation of novel coronaviruses, the infectivity of virulent strains is greatly enhanced, which also affects the adaptability of the aforementioned prediction methods.…”

Section: Introduction and Reviewmentioning

confidence: 99%

Epidemic prediction based on entropy-improved factor analysis and WOA-optimized BP network algorithm

Jianan,

Hongyi,

Bingsong

2023

International Conference on Computer, Artificial Intelligence, and Control Engineering (CAICE 2023)

View full text Add to dashboard Cite

The new Coronavirus epidemic has had a huge impact on the economy, politics, and culture worldwide. However, it is very difficult to obtain accurate data on the new crown epidemic due to various uncertainties, such as the difficulty of detection. In this paper, we use objective and real Baidu search indexes as the basic data set and use factor analysis with the improvement of entropy method to reduce the dimensionality of Baidu search index data to solve the problem of fixed parameters caused by its excessive dimensionality. After that, the WOA algorithm is used to optimize the parameters of the conventional BP neural network, thus making the fit and accuracy greatly improved, which is of great practical significance for the prediction of epidemic data.

show abstract

“…For the intelligent optimization algorithms, the balance degree of exploration and development directly affects the convergence speed and optimization ability of the algorithm, and also determines the advantages and disadvantages of the algorithm. At the end of the 20th century, meta-heuristic algorithms have gradually become prominent, such as Genetic Algorithm [1] (GA), Ant Colony Optimization Algorithm [2] (ACO), Particle Swarm Optimization algorithm [3] (PSO), Glowworm Swarm Optimization algorithm [4] (GSO), etc. The meta-heuristic intelligent optimization algorithms imitate the reproduction and evolution process of various organisms in nature, such as fish, ant colonies, fireflies, etc., to find the optimal solution to the problem.…”

Section: Introductionmentioning

confidence: 99%

An Improved Cuckoo Search Algorithm Based on Elite Opposition-based Learning for Indoor Visible Light Positioning

Yang Yang,

Mao-Sheng Fu

et al. 2023

Journal of Computers

View full text Add to dashboard Cite

<p>In the cuckoo search algorithm, the structure is simple, and the parameters are not much, but it is easy to trap into the local optimum, and in the later period, the convergence speed is plodding. Aiming at the shortcomings of the standard cuckoo algorithm, a modified cuckoo algorithm (EACSDAM) is presented in this paper, which adopts elite reverse learning to enhance the population diversity, and increases the step factor and discovery probability to improve the global detection and local searchability. Eight standard test functions are used to simulate the EACSDAM algorithm. Compared with the standard cuckoo algorithm and the other two improved algorithms, the accuracy and convergence speed of EACSDAM are greatly improved. In the end, EACSDAM is used to optimize the indoor 3D visible light positioning. The simulation results indicate that EACSDAM has a more powerful ability for global optimization, and more accurate positioning, and the positioning error is significantly reduced.</p> <p> </p>

show abstract

Application of improved Q learning algorithm to job shop problem

Cited by 4 publications

References 1 publication

A self‐learning artificial bee colony algorithm based on reinforcement learning for a flexible job‐shop scheduling problem

A self‐learning artificial bee colony algorithm based on reinforcement learning for a flexible job‐shop scheduling problem

Epidemic prediction based on entropy-improved factor analysis and WOA-optimized BP network algorithm

An Improved Cuckoo Search Algorithm Based on Elite Opposition-based Learning for Indoor Visible Light Positioning

Contact Info

Product

Resources

About